PROJECT

# get information of the datatypes
# if there is any class data in the features,convert them into binary form
# look how ages of the data are looking and some information
# get the descriptive statistics of the above data
# construct the histogram, boxplot for every column using for loop
# get the corelation heatmap and find if there is association between certain columns
# choose the specific columns which have certain association and get the pairplot

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")

r=pd.read_csv("C:\\Users\\ruchi\\Downloads\\Minsk2020_ALS_dataset.csv")

r

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Diagnosis (ALS)
0	8	M	58	0.321817	0.141230	0.199128	0.923634	6.044559	3.196477	3.770575	...	-0.024467	-0.005300	0.051874	-0.037710	-0.026549	-0.021149	4.825476	2526.285657	833.498083	1
1	20	F	57	0.344026	0.177032	0.206458	0.827714	1.967728	0.856639	1.179851	...	0.002485	-0.004535	-0.000225	-0.006977	-0.012510	0.014773	5.729322	1985.712014	561.802625	1
2	21	F	58	0.264740	0.148228	0.177078	0.532566	1.850893	0.942743	1.071950	...	-0.013927	0.007908	0.007960	-0.009022	-0.012488	-0.015588	8.258488	2364.695972	796.723440	1
3	22	F	70	0.455793	0.174870	0.243660	0.962641	2.883768	1.284926	1.915058	...	-0.019285	-0.021768	0.020495	0.035976	-0.034648	0.008021	5.447137	1860.172768	359.409974	1
4	24	M	66	0.269335	0.143961	0.167465	0.547745	2.327924	1.164109	1.420891	...	-0.005743	0.004726	-0.015247	0.003900	-0.007686	-0.003784	8.562517	2051.627447	817.111847	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
59	123	M	43	0.255799	0.123679	0.182658	0.505591	6.222031	2.876602	3.894294	...	0.220533	0.089766	-0.120838	-0.004221	-0.013165	0.004642	9.855665	3128.341308	1990.937097	0
60	125	M	63	0.513175	0.296489	0.334845	0.729804	9.686563	4.327943	5.687977	...	0.028016	-0.038739	0.011588	-0.011281	-0.004294	0.011239	11.094558	1964.218942	601.076046	0
61	127	F	67	0.383901	0.245923	0.251359	0.415136	4.148414	2.069757	2.527213	...	0.011685	0.007883	-0.014839	0.013859	0.011145	0.001418	12.564742	2526.285657	934.343638	0
62	129	F	68	1.336216	0.815757	0.733197	0.981928	11.224542	5.295879	6.994751	...	0.015712	0.013437	0.025113	0.008852	-0.010132	-0.008458	10.670669	3201.250289	2284.051658	0
63	131	F	60	0.916706	0.566121	0.512857	1.467165	6.372832	3.251168	3.539229	...	-0.046235	0.041946	-0.065313	-0.016682	0.061026	-0.005883	6.972152	2792.655884	1518.529172	0

64 rows × 135 columns

r=pd.DataFrame(r)

r.head()  ##first five rows

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Diagnosis (ALS)
0	8	M	58	0.321817	0.141230	0.199128	0.923634	6.044559	3.196477	3.770575	...	-0.024467	-0.005300	0.051874	-0.037710	-0.026549	-0.021149	4.825476	2526.285657	833.498083	1
1	20	F	57	0.344026	0.177032	0.206458	0.827714	1.967728	0.856639	1.179851	...	0.002485	-0.004535	-0.000225	-0.006977	-0.012510	0.014773	5.729322	1985.712014	561.802625	1
2	21	F	58	0.264740	0.148228	0.177078	0.532566	1.850893	0.942743	1.071950	...	-0.013927	0.007908	0.007960	-0.009022	-0.012488	-0.015588	8.258488	2364.695972	796.723440	1
3	22	F	70	0.455793	0.174870	0.243660	0.962641	2.883768	1.284926	1.915058	...	-0.019285	-0.021768	0.020495	0.035976	-0.034648	0.008021	5.447137	1860.172768	359.409974	1
4	24	M	66	0.269335	0.143961	0.167465	0.547745	2.327924	1.164109	1.420891	...	-0.005743	0.004726	-0.015247	0.003900	-0.007686	-0.003784	8.562517	2051.627447	817.111847	1

5 rows × 135 columns

r.tail()   ##last five rows

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Diagnosis (ALS)
59	123	M	43	0.255799	0.123679	0.182658	0.505591	6.222031	2.876602	3.894294	...	0.220533	0.089766	-0.120838	-0.004221	-0.013165	0.004642	9.855665	3128.341308	1990.937097	0
60	125	M	63	0.513175	0.296489	0.334845	0.729804	9.686563	4.327943	5.687977	...	0.028016	-0.038739	0.011588	-0.011281	-0.004294	0.011239	11.094558	1964.218942	601.076046	0
61	127	F	67	0.383901	0.245923	0.251359	0.415136	4.148414	2.069757	2.527213	...	0.011685	0.007883	-0.014839	0.013859	0.011145	0.001418	12.564742	2526.285657	934.343638	0
62	129	F	68	1.336216	0.815757	0.733197	0.981928	11.224542	5.295879	6.994751	...	0.015712	0.013437	0.025113	0.008852	-0.010132	-0.008458	10.670669	3201.250289	2284.051658	0
63	131	F	60	0.916706	0.566121	0.512857	1.467165	6.372832	3.251168	3.539229	...	-0.046235	0.041946	-0.065313	-0.016682	0.061026	-0.005883	6.972152	2792.655884	1518.529172	0

5 rows × 135 columns

r.info()  

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 64 entries, 0 to 63
Columns: 135 entries, ID to Diagnosis (ALS)
dtypes: float64(131), int64(3), object(1)
memory usage: 67.6+ KB

r.shape

(64, 135)

r.isnull().sum().sort_values(ascending=False) ##if null values are there are not

ID                 0
Hi(3)_{mu}         0
Hi(1)_{rel}        0
Hi(8)_{sd}         0
Hi(7)_{sd}         0
                  ..
Ha(5)_{rel}        0
Ha(4)_{rel}        0
Ha(3)_{rel}        0
Ha(2)_{rel}        0
Diagnosis (ALS)    0
Length: 135, dtype: int64

r.columns

Index(['ID', 'Sex', 'Age', 'J1_a', 'J3_a', 'J5_a', 'J55_a', 'S1_a', 'S3_a',
       'S5_a',
       ...
       'dCCi(7)', 'dCCi(8)', 'dCCi(9)', 'dCCi(10)', 'dCCi(11)', 'dCCi(12)',
       'd_1', 'F2_i', 'F2_{conv}', 'Diagnosis (ALS)'],
      dtype='object', length=135)

for i in r.columns:  ##see the all columns names eith data types
    print(f"'{i}' data type:{r[i].dtypes}")

'ID' data type:int64
'Sex' data type:object
'Age' data type:int64
'J1_a' data type:float64
'J3_a' data type:float64
'J5_a' data type:float64
'J55_a' data type:float64
'S1_a' data type:float64
'S3_a' data type:float64
'S5_a' data type:float64
'S11_a' data type:float64
'S55_a' data type:float64
'DPF_a' data type:float64
'PFR_a' data type:float64
'PPE_a' data type:float64
'PVI_a' data type:float64
'HNR_a' data type:float64
'GNEa_{\mu}' data type:float64
'GNEa_{\sigma}' data type:float64
'Ha(1)_{mu}' data type:float64
'Ha(2)_{mu}' data type:float64
'Ha(3)_{mu}' data type:float64
'Ha(4)_{mu}' data type:float64
'Ha(5)_{mu}' data type:float64
'Ha(6)_{mu}' data type:float64
'Ha(7)_{mu}' data type:float64
'Ha(8)_{mu}' data type:float64
'Ha(1)_{sd}' data type:float64
'Ha(2)_{sd}' data type:float64
'Ha(3)_{sd}' data type:float64
'Ha(4)_{sd}' data type:float64
'Ha(5)_{sd}' data type:float64
'Ha(6)_{sd}' data type:float64
'Ha(7)_{sd}' data type:float64
'Ha(8)_{sd}' data type:float64
'Ha(1)_{rel}' data type:float64
'Ha(2)_{rel}' data type:float64
'Ha(3)_{rel}' data type:float64
'Ha(4)_{rel}' data type:float64
'Ha(5)_{rel}' data type:float64
'Ha(6)_{rel}' data type:float64
'Ha(7)_{rel}' data type:float64
'Ha(8)_{rel}' data type:float64
'CCa(1)' data type:float64
'CCa(2)' data type:float64
'CCa(3)' data type:float64
'CCa(4)' data type:float64
'CCa(5)' data type:float64
'CCa(6)' data type:float64
'CCa(7)' data type:float64
'CCa(8)' data type:float64
'CCa(9)' data type:float64
'CCa(10)' data type:float64
'CCa(11)' data type:float64
'CCa(12)' data type:float64
'dCCa(1)' data type:float64
'dCCa(2)' data type:float64
'dCCa(3)' data type:float64
'dCCa(4)' data type:float64
'dCCa(5)' data type:float64
'dCCa(6)' data type:float64
'dCCa(7)' data type:float64
'dCCa(8)' data type:float64
'dCCa(9)' data type:float64
'dCCa(10)' data type:float64
'dCCa(11)' data type:float64
'dCCa(12)' data type:float64
'J1_i' data type:float64
'J3_i' data type:float64
'J5_i' data type:float64
'J55_i' data type:float64
'S1_i' data type:float64
'S3_i' data type:float64
'S5_i' data type:float64
'S11_i' data type:float64
'S55_i' data type:float64
'DPF_i' data type:float64
'PFR_i' data type:float64
'PPE_i' data type:float64
'PVI_i' data type:float64
'HNR_i' data type:float64
'GNEi_{\mu}' data type:float64
'GNEi_{\sigma}' data type:float64
'Hi(1)_{mu}' data type:float64
'Hi(2)_{mu}' data type:float64
'Hi(3)_{mu}' data type:float64
'Hi(4)_{mu}' data type:float64
'Hi(5)_{mu}' data type:float64
'Hi(6)_{mu}' data type:float64
'Hi(7)_{mu}' data type:float64
'Hi(8)_{mu}' data type:float64
'Hi(1)_{sd}' data type:float64
'Hi(2)_{sd}' data type:float64
'Hi(3)_{sd}' data type:float64
'Hi(4)_{sd}' data type:float64
'Hi(5)_{sd}' data type:float64
'Hi(6)_{sd}' data type:float64
'Hi(7)_{sd}' data type:float64
'Hi(8)_{sd}' data type:float64
'Hi(1)_{rel}' data type:float64
'Hi(2)_{rel}' data type:float64
'Hi(3)_{rel}' data type:float64
'Hi(4)_{rel}' data type:float64
'Hi(5)_{rel}' data type:float64
'Hi(6)_{rel}' data type:float64
'Hi(7)_{rel}' data type:float64
'Hi(8)_{rel}' data type:float64
'CCi(1)' data type:float64
'CCi(2)' data type:float64
'CCi(3)' data type:float64
'CCi(4)' data type:float64
'CCi(5)' data type:float64
'CCi(6)' data type:float64
'CCi(7)' data type:float64
'CCi(8)' data type:float64
'CCi(9)' data type:float64
'CCi(10)' data type:float64
'CCi(11)' data type:float64
'CCi(12)' data type:float64
'dCCi(1)' data type:float64
'dCCi(2)' data type:float64
'dCCi(3)' data type:float64
'dCCi(4)' data type:float64
'dCCi(5)' data type:float64
'dCCi(6)' data type:float64
'dCCi(7)' data type:float64
'dCCi(8)' data type:float64
'dCCi(9)' data type:float64
'dCCi(10)' data type:float64
'dCCi(11)' data type:float64
'dCCi(12)' data type:float64
'd_1' data type:float64
'F2_i' data type:float64
'F2_{conv}' data type:float64
'Diagnosis (ALS)' data type:int64

r["Sex"].value_counts() ##showing the count of gender

Sex
F    34
M    30
Name: count, dtype: int64

print(r.dtypes) ##data type

ID                   int64
Sex                 object
Age                  int64
J1_a               float64
J3_a               float64
                    ...   
dCCi(12)           float64
d_1                float64
F2_i               float64
F2_{conv}          float64
Diagnosis (ALS)      int64
Length: 135, dtype: object

x=r.iloc[:,:-1]                       ##spliting it into training and testing data
y=r.iloc[:,-1]
print("training data:",x)
print("              "*3)
print("testing data:",y)

training data:      ID Sex  Age      J1_a      J3_a      J5_a     J55_a       S1_a      S3_a  \
0     8   M   58  0.321817  0.141230  0.199128  0.923634   6.044559  3.196477   
1    20   F   57  0.344026  0.177032  0.206458  0.827714   1.967728  0.856639   
2    21   F   58  0.264740  0.148228  0.177078  0.532566   1.850893  0.942743   
3    22   F   70  0.455793  0.174870  0.243660  0.962641   2.883768  1.284926   
4    24   M   66  0.269335  0.143961  0.167465  0.547745   2.327924  1.164109   
..  ...  ..  ...       ...       ...       ...       ...        ...       ...   
59  123   M   43  0.255799  0.123679  0.182658  0.505591   6.222031  2.876602   
60  125   M   63  0.513175  0.296489  0.334845  0.729804   9.686563  4.327943   
61  127   F   67  0.383901  0.245923  0.251359  0.415136   4.148414  2.069757   
62  129   F   68  1.336216  0.815757  0.733197  0.981928  11.224542  5.295879   
63  131   F   60  0.916706  0.566121  0.512857  1.467165   6.372832  3.251168   

        S5_a  ...   dCCi(6)   dCCi(7)   dCCi(8)   dCCi(9)  dCCi(10)  dCCi(11)  \
0   3.770575  ...  0.016809 -0.024467 -0.005300  0.051874 -0.037710 -0.026549   
1   1.179851  ...  0.019235  0.002485 -0.004535 -0.000225 -0.006977 -0.012510   
2   1.071950  ...  0.007199 -0.013927  0.007908  0.007960 -0.009022 -0.012488   
3   1.915058  ...  0.013213 -0.019285 -0.021768  0.020495  0.035976 -0.034648   
4   1.420891  ...  0.002948 -0.005743  0.004726 -0.015247  0.003900 -0.007686   
..       ...  ...       ...       ...       ...       ...       ...       ...   
59  3.894294  ... -0.060395  0.220533  0.089766 -0.120838 -0.004221 -0.013165   
60  5.687977  ... -0.046223  0.028016 -0.038739  0.011588 -0.011281 -0.004294   
61  2.527213  ... -0.005008  0.011685  0.007883 -0.014839  0.013859  0.011145   
62  6.994751  ...  0.025679  0.015712  0.013437  0.025113  0.008852 -0.010132   
63  3.539229  ... -0.072828 -0.046235  0.041946 -0.065313 -0.016682  0.061026   

    dCCi(12)        d_1         F2_i    F2_{conv}  
0  -0.021149   4.825476  2526.285657   833.498083  
1   0.014773   5.729322  1985.712014   561.802625  
2  -0.015588   8.258488  2364.695972   796.723440  
3   0.008021   5.447137  1860.172768   359.409974  
4  -0.003784   8.562517  2051.627447   817.111847  
..       ...        ...          ...          ...  
59  0.004642   9.855665  3128.341308  1990.937097  
60  0.011239  11.094558  1964.218942   601.076046  
61  0.001418  12.564742  2526.285657   934.343638  
62 -0.008458  10.670669  3201.250289  2284.051658  
63 -0.005883   6.972152  2792.655884  1518.529172  

[64 rows x 134 columns]
                                          
testing data: 0     1
1     1
2     1
3     1
4     1
     ..
59    0
60    0
61    0
62    0
63    0
Name: Diagnosis (ALS), Length: 64, dtype: int64

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=1,test_size=0.15,stratify=y)

x_train

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(6)	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}
14	52	F	62	1.394205	0.839935	0.703224	1.362995	4.661601	2.402909	2.826132	...	-0.000823	0.025207	-0.002524	-0.006103	-0.012850	-0.015023	0.019711	12.862700	3092.653846	1552.852150
10	39	M	67	1.232990	0.561293	0.784691	1.889785	4.139457	1.915796	2.692091	...	0.031624	-0.018089	0.018493	0.006547	-0.004817	-0.003710	-0.000692	2.276702	1686.160000	669.461749
59	123	M	43	0.255799	0.123679	0.182658	0.505591	6.222031	2.876602	3.894294	...	-0.060395	0.220533	0.089766	-0.120838	-0.004221	-0.013165	0.004642	9.855665	3128.341308	1990.937097
35	24	M	60	0.391222	0.200687	0.232286	0.638498	2.324343	1.181015	1.475889	...	-0.005405	-0.006063	0.028443	-0.006618	0.003011	-0.005547	-0.002806	10.525555	2700.419449	1393.549002
44	77	F	40	0.349185	0.213207	0.227957	0.347673	3.395795	1.826527	2.123809	...	-0.042489	-0.021018	0.049357	0.005870	-0.027345	-0.026138	0.009430	10.594026	3515.050257	1925.062482
26	94	F	55	0.764443	0.423008	0.472764	1.699466	8.254286	3.966819	5.010081	...	0.018794	0.036827	0.029426	-0.024056	-0.065735	0.012986	0.012941	9.482607	2471.097222	1019.521207
20	72	F	64	0.797801	0.470116	0.522910	1.663179	7.778152	3.640445	4.355894	...	0.028207	-0.052002	-0.038210	0.028143	0.033156	0.010924	0.020823	5.924309	1880.538263	482.819916
27	96	F	52	0.475047	0.308491	0.266091	0.396462	3.686641	1.999494	2.083195	...	0.009989	0.000009	0.042347	-0.003170	0.002103	0.011023	-0.031324	11.597077	2792.655884	1457.933269
3	22	F	70	0.455793	0.174870	0.243660	0.962641	2.883768	1.284926	1.915058	...	0.013213	-0.019285	-0.021768	0.020495	0.035976	-0.034648	0.008021	5.447137	1860.172768	359.409974
23	80	F	63	0.504802	0.253832	0.313823	1.229761	6.571067	2.833840	4.277576	...	0.013513	-0.003382	0.027770	-0.005112	-0.027102	0.012612	-0.010165	7.339732	3556.978755	2129.076098
4	24	M	66	0.269335	0.143961	0.167465	0.547745	2.327924	1.164109	1.420891	...	0.002948	-0.005743	0.004726	-0.015247	0.003900	-0.007686	-0.003784	8.562517	2051.627447	817.111847
53	111	F	60	0.121065	0.079473	0.101627	0.285497	1.117740	0.558948	0.615284	...	-0.005255	0.017626	-0.007311	-0.006541	-0.012625	0.013987	0.014222	11.261019	3201.250289	1960.299963
34	16	M	38	0.415366	0.254119	0.243906	0.449362	2.394697	1.292778	1.468358	...	0.000016	0.008047	-0.005823	-0.006588	-0.000030	0.003137	-0.002440	8.531677	3515.050257	2441.219054
41	61	F	37	0.818954	0.484998	0.511515	0.721296	4.942091	2.724820	3.320166	...	0.005945	0.021267	-0.008438	0.007339	-0.004838	-0.004133	0.000937	10.151495	2444.009071	1157.993834
57	119	F	65	0.356684	0.233194	0.242305	0.410246	3.251335	1.867689	1.908461	...	0.005494	-0.003761	0.006982	0.012774	0.008384	0.002823	-0.014323	10.889792	2471.097222	1549.074209
62	129	F	68	1.336216	0.815757	0.733197	0.981928	11.224542	5.295879	6.994751	...	0.025679	0.015712	0.013437	0.025113	0.008852	-0.010132	-0.008458	10.670669	3201.250289	2284.051658
51	107	M	80	0.532330	0.296012	0.322217	0.650045	8.042171	4.754839	5.060159	...	-0.014078	0.010696	-0.003448	-0.015049	0.010195	-0.002152	0.001881	9.472404	2238.670803	1241.852695
37	28	M	35	0.758571	0.464961	0.413086	0.605323	9.271523	5.707370	5.150374	...	-0.003686	0.018992	0.034957	0.016890	-0.009376	-0.008998	-0.007465	12.892692	2888.617021	1653.804580
13	48	F	63	0.805433	0.335434	0.487871	1.813700	4.485662	2.192828	2.864096	...	0.005770	-0.028306	-0.035823	-0.004287	-0.014985	-0.004156	-0.005061	7.029500	2730.764545	1288.920905
7	28	M	58	1.210548	0.726523	0.661670	1.205596	8.492104	4.109625	5.377768	...	0.007534	0.017088	0.015907	-0.006379	0.057303	-0.001919	-0.008007	8.422353	1964.218942	759.068477
33	6	M	41	1.063272	0.683918	0.504427	0.613402	3.176717	1.870164	1.590798	...	0.017293	-0.008880	-0.001511	0.003965	0.015240	-0.006500	-0.008723	10.482453	2263.284796	801.333727
60	125	M	63	0.513175	0.296489	0.334845	0.729804	9.686563	4.327943	5.687977	...	-0.046223	0.028016	-0.038739	0.011588	-0.011281	-0.004294	0.011239	11.094558	1964.218942	601.076046
50	99	F	57	0.098881	0.065791	0.092655	0.363699	0.883453	0.449099	0.497111	...	0.015152	-0.027019	0.037807	-0.019812	0.000436	-0.002840	-0.013161	10.108459	2143.018556	805.694015
15	55	M	61	1.177795	0.730069	0.569287	1.542224	5.883227	3.384535	2.875918	...	0.028733	-0.004708	-0.004383	0.006398	-0.014412	-0.005085	0.005530	7.148809	2051.627447	784.563460
9	32	M	61	0.387730	0.213745	0.249993	0.591160	3.351240	1.874979	2.075762	...	0.004241	0.006956	-0.002013	-0.000082	0.008275	-0.013829	-0.006955	7.572111	1780.825796	838.978523
32	4	F	53	0.598550	0.350577	0.378646	0.654399	4.224992	2.312947	2.678596	...	0.001768	-0.003924	0.001995	0.004019	-0.007207	0.004614	0.003154	7.615608	2921.471038	1230.982918
45	81	F	60	0.286517	0.176603	0.195712	0.692300	1.847736	0.869278	1.099434	...	0.023767	-0.020693	0.019078	-0.034556	-0.006731	-0.025442	-0.005668	12.874560	2670.464441	1309.871125
52	109	F	59	0.326851	0.215126	0.182667	0.304952	2.801295	1.669496	1.509331	...	-0.000688	-0.018500	0.030142	0.002111	0.006603	-0.013728	-0.021879	8.064921	2700.419449	1228.586973
18	64	M	57	0.426554	0.202661	0.255198	0.885479	4.387137	1.892587	2.628737	...	0.003446	0.010420	0.005288	-0.006713	0.013147	-0.017816	0.017087	11.136041	2238.670803	930.223353
5	25	M	51	0.339593	0.182070	0.204186	0.505987	1.969217	0.834783	1.208688	...	0.009548	-0.005489	0.010164	-0.008341	-0.006132	0.005441	0.003568	9.810520	2143.018556	1004.727725
29	100	M	69	0.511742	0.313666	0.320677	0.431433	7.417198	4.258109	4.961685	...	-0.013859	0.000308	-0.038984	0.048771	-0.014493	0.008647	-0.004524	2.512995	1233.583584	48.246203
24	84	F	55	0.419330	0.255329	0.338319	0.486463	4.366452	1.932596	2.855240	...	-0.005714	0.012337	-0.005475	-0.001179	-0.002687	0.005369	0.034289	11.766102	2888.617021	1839.961952
19	68	M	40	0.496922	0.213975	0.293201	0.957065	3.293700	1.672811	1.894214	...	0.023989	-0.030137	0.024769	0.000567	0.005071	-0.023693	0.009770	7.872279	2143.018556	985.160918
30	102	F	53	0.561542	0.331788	0.345130	1.020709	6.074875	2.798090	3.526055	...	0.022664	0.008537	-0.000306	-0.012570	-0.048113	0.009073	-0.005201	12.036001	2526.285657	1200.269866
54	113	F	62	0.823780	0.503064	0.497916	0.704065	6.861939	3.993216	4.174705	...	0.014494	0.003410	0.000716	-0.010791	0.004878	-0.005527	-0.001659	7.388631	2096.808356	737.085571
6	27	M	57	0.691093	0.406901	0.406287	0.765986	6.168256	3.702088	3.286232	...	0.002661	-0.012605	0.013385	0.004513	0.001568	-0.008244	0.005801	5.945219	2313.388825	1219.744513
48	89	F	45	0.155762	0.091831	0.117099	0.575170	1.575403	0.738640	0.834830	...	0.002348	-0.002313	0.008766	0.006330	0.016645	-0.003417	0.002115	10.713432	3599.554394	2226.127951
2	21	F	58	0.264740	0.148228	0.177078	0.532566	1.850893	0.942743	1.071950	...	0.007199	-0.013927	0.007908	0.007960	-0.009022	-0.012488	-0.015588	8.258488	2364.695972	796.723440
12	46	F	50	0.199868	0.132266	0.157546	0.454599	1.467287	0.706004	0.819799	...	0.001819	0.011291	-0.001916	0.001513	-0.002502	0.002014	0.010446	10.950821	3164.536485	1553.425003
55	115	F	50	0.462076	0.269359	0.296952	0.909990	5.020638	2.305690	2.837745	...	0.001699	-0.001674	0.012043	-0.003015	0.022928	-0.005444	-0.006394	14.651111	3515.050257	2210.936432
22	78	F	64	0.437128	0.265519	0.349086	0.493971	3.205305	1.515726	2.119909	...	-0.060397	0.056134	-0.069202	-0.040180	-0.058987	0.044552	0.077897	2.986929	1800.351911	784.205580
49	97	F	39	0.463874	0.290374	0.278926	0.550290	2.449028	1.372602	1.412486	...	-0.000234	0.011520	0.009453	0.002072	-0.002811	0.004577	-0.009058	10.616077	3164.536485	2037.766311
28	98	M	68	1.076446	0.624824	0.561100	1.965493	7.001105	3.785627	4.033533	...	-0.011602	0.018274	0.004485	0.005101	-0.007367	0.007041	-0.001560	11.097431	3515.050257	2157.871393
46	85	F	55	0.454844	0.289458	0.293609	0.582757	2.124786	1.170689	1.182154	...	0.006111	0.003214	0.007520	-0.024862	0.016600	-0.015827	0.002088	12.189059	3092.653846	1551.286187
16	58	M	58	5.391649	3.217293	3.321567	5.991336	29.441589	16.791944	18.368778	...	-0.002691	0.008994	0.025390	0.040231	0.003503	-0.006546	-0.024835	8.008742	1921.927690	583.380671
63	131	F	60	0.916706	0.566121	0.512857	1.467165	6.372832	3.251168	3.539229	...	-0.072828	-0.046235	0.041946	-0.065313	-0.016682	0.061026	-0.005883	6.972152	2792.655884	1518.529172
21	76	M	68	0.379367	0.223560	0.308426	1.821009	5.539475	2.551095	3.000675	...	0.008846	-0.006281	-0.004169	-0.008164	0.012667	-0.015442	0.001157	5.218871	1649.621788	177.843734
58	121	F	67	0.237654	0.154117	0.154312	0.544602	3.583597	1.690501	1.840416	...	-0.027062	-0.002917	0.020006	-0.064556	0.014446	0.015248	-0.013882	9.311776	2670.464441	1087.940178
61	127	F	67	0.383901	0.245923	0.251359	0.415136	4.148414	2.069757	2.527213	...	-0.005008	0.011685	0.007883	-0.014839	0.013859	0.011145	0.001418	12.564742	2526.285657	934.343638
38	42	M	60	0.182721	0.089174	0.113216	0.651748	1.839764	0.673977	1.084464	...	0.021454	0.007635	0.019134	0.013320	0.002002	-0.022146	0.005825	15.420777	2313.388825	1381.628235
11	42	M	67	1.608454	0.989100	0.894706	1.304613	6.031953	3.279233	3.729620	...	0.019701	0.004293	0.026891	0.080337	-0.007352	0.055993	0.075071	10.674106	2007.441819	481.009629
47	86	F	63	0.753234	0.467912	0.442792	0.540327	4.801768	2.677700	3.241265	...	-0.018937	0.011239	0.011488	0.015334	0.008337	0.005474	0.011687	10.515820	3057.463491	1494.054076
31	2	F	64	0.219429	0.144385	0.171661	0.555528	2.054277	1.108746	1.260472	...	-0.011558	-0.004168	0.018603	0.019350	0.016342	0.014127	0.022756	10.121803	2988.533127	1332.559788
56	117	M	49	0.319535	0.143602	0.193376	0.846877	4.171980	1.868911	2.581316	...	-0.033465	0.019372	-0.041478	0.004583	-0.013913	-0.007205	0.013409	10.286022	1985.712014	804.666593

54 rows × 134 columns

x_test

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(6)	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}
8	31	M	67	0.537010	0.243234	0.318075	1.951256	6.568645	2.891654	4.620345	...	0.014234	0.013594	-0.003722	-0.003859	-0.011985	-0.027240	0.002325	8.760510	1840.022120	669.022078
39	49	M	38	0.176448	0.103346	0.123381	0.649644	2.649815	1.410593	1.504265	...	0.016461	0.014798	-0.011568	-0.009276	-0.003996	-0.003248	-0.005049	10.074644	2119.782609	580.338238
25	92	F	39	2.061820	1.219720	1.280772	1.306779	15.095252	7.876805	9.839396	...	0.009492	-0.033642	-0.032431	-0.056497	-0.003210	0.019443	0.004703	7.986808	3164.536485	1734.620853
17	62	M	57	0.351191	0.165077	0.227554	0.849025	3.695872	1.776465	2.379529	...	0.024865	-0.008019	0.005046	0.023446	-0.000726	-0.016418	0.010174	6.031056	2074.091402	927.063276
40	53	M	60	0.487857	0.208116	0.282759	1.183502	4.734293	2.542676	3.053723	...	-0.003976	0.001242	0.005562	-0.000695	0.003333	0.004020	-0.005159	9.943562	2471.097222	1212.922300
1	20	F	57	0.344026	0.177032	0.206458	0.827714	1.967728	0.856639	1.179851	...	0.019235	0.002485	-0.004535	-0.000225	-0.006977	-0.012510	0.014773	5.729322	1985.712014	561.802625
36	26	M	34	0.163026	0.094282	0.112654	0.378197	2.617874	1.361172	1.550565	...	-0.010711	0.006573	0.003950	-0.003954	0.001273	0.005890	0.000385	8.471564	2700.419449	1293.468915
42	63	F	50	0.323175	0.126138	0.176197	0.907850	3.069980	1.372204	1.869070	...	0.004152	-0.001733	0.030566	-0.037259	-0.020167	-0.042955	-0.083977	9.167460	444.730268	1169.075556
43	65	M	52	1.529994	0.894926	0.809959	1.715071	7.627483	4.321696	4.415383	...	0.015596	-0.012218	0.015828	-0.014697	0.010636	0.004654	-0.003235	7.758796	2761.507400	1641.852909
0	8	M	58	0.321817	0.141230	0.199128	0.923634	6.044559	3.196477	3.770575	...	0.016809	-0.024467	-0.005300	0.051874	-0.037710	-0.026549	-0.021149	4.825476	2526.285657	833.498083

10 rows × 134 columns

y_train

14    1
10    1
59    0
35    0
44    0
26    1
20    1
27    1
3     1
23    1
4     1
53    0
34    0
41    0
57    0
62    0
51    0
37    0
13    1
7     1
33    0
60    0
50    0
15    1
9     1
32    0
45    0
52    0
18    1
5     1
29    1
24    1
19    1
30    1
54    0
6     1
48    0
2     1
12    1
55    0
22    1
49    0
28    1
46    0
16    1
63    0
21    1
58    0
61    0
38    0
11    1
47    0
31    0
56    0
Name: Diagnosis (ALS), dtype: int64

y_test

8     1
39    0
25    1
17    1
40    0
1     1
36    0
42    0
43    0
0     1
Name: Diagnosis (ALS), dtype: int64

print(r.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 64 entries, 0 to 63
Columns: 135 entries, ID to Diagnosis (ALS)
dtypes: float64(131), int64(3), object(1)
memory usage: 67.6+ KB
None

plt.figure(figsize=(20,10))
age=sns.countplot(x="Age",data=r)
for bars in age.containers:
    age.bar_label(bars)

gender=sns.countplot(x="Sex",data=r)
for bars in gender.containers:
    gender.bar_label(bars)

r["Sex"]=r["Sex"].replace({"M": 0,"F": 1})   ##categorical to binary

r["Sex"]

0     0
1     1
2     1
3     1
4     0
     ..
59    0
60    0
61    1
62    1
63    1
Name: Sex, Length: 64, dtype: int64

r.head()

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Diagnosis (ALS)
0	8	0	58	0.321817	0.141230	0.199128	0.923634	6.044559	3.196477	3.770575	...	-0.024467	-0.005300	0.051874	-0.037710	-0.026549	-0.021149	4.825476	2526.285657	833.498083	1
1	20	1	57	0.344026	0.177032	0.206458	0.827714	1.967728	0.856639	1.179851	...	0.002485	-0.004535	-0.000225	-0.006977	-0.012510	0.014773	5.729322	1985.712014	561.802625	1
2	21	1	58	0.264740	0.148228	0.177078	0.532566	1.850893	0.942743	1.071950	...	-0.013927	0.007908	0.007960	-0.009022	-0.012488	-0.015588	8.258488	2364.695972	796.723440	1
3	22	1	70	0.455793	0.174870	0.243660	0.962641	2.883768	1.284926	1.915058	...	-0.019285	-0.021768	0.020495	0.035976	-0.034648	0.008021	5.447137	1860.172768	359.409974	1
4	24	0	66	0.269335	0.143961	0.167465	0.547745	2.327924	1.164109	1.420891	...	-0.005743	0.004726	-0.015247	0.003900	-0.007686	-0.003784	8.562517	2051.627447	817.111847	1

5 rows × 135 columns

stats=r.describe().T ##statistics

print(stats)

                 count         mean         std         min          25%  \
ID                64.0    67.875000   37.358198    2.000000    31.750000   
Sex               64.0     0.531250    0.502967    0.000000     0.000000   
Age               64.0    56.390625   10.203668   34.000000    50.750000   
J1_a              64.0     0.658951    0.724002    0.098881     0.325932   
J3_a              64.0     0.379242    0.435636    0.065791     0.172422   
...                ...          ...         ...         ...          ...   
dCCi(12)          64.0     0.001269    0.020800   -0.083977    -0.006534   
d_1               64.0     9.164473    2.681449    2.276702     7.604734   
F2_i              64.0  2495.116475  617.755856  444.730268  2051.627447   
F2_{conv}         64.0  1209.976405  553.694046   48.246203   800.181156   
Diagnosis (ALS)   64.0     0.484375    0.503706    0.000000     0.000000   

                         50%          75%          max  
ID                 66.500000    98.250000   131.000000  
Sex                 1.000000     1.000000     1.000000  
Age                58.000000    63.250000    80.000000  
J1_a                0.458935     0.772783     5.391649  
J3_a                0.253976     0.465699     3.217293  
...                      ...          ...          ...  
dCCi(12)            0.000661     0.009515     0.077897  
d_1                 9.646564    10.757522    15.420777  
F2_i             2471.097222  2938.236560  3599.554394  
F2_{conv}        1206.596083  1551.677678  2441.219054  
Diagnosis (ALS)     0.000000     1.000000     1.000000  

[135 rows x 8 columns]

r.mode()

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Diagnosis (ALS)
0	24.0	1.0	60.0	0.098881	0.065791	0.092655	0.285497	0.883453	0.449099	0.497111	...	-0.052002	-0.069202	-0.120838	-0.065735	-0.042955	-0.083977	2.276702	3515.050257	48.246203	0.0
1	28.0	NaN	NaN	0.121065	0.079473	0.101627	0.304952	1.117740	0.558948	0.615284	...	-0.046235	-0.041478	-0.065313	-0.058987	-0.034648	-0.031324	2.512995	NaN	177.843734	NaN
2	42.0	NaN	NaN	0.155762	0.089174	0.112654	0.347673	1.467287	0.673977	0.819799	...	-0.033642	-0.038984	-0.064556	-0.048113	-0.027240	-0.024835	2.986929	NaN	359.409974	NaN
3	NaN	NaN	NaN	0.163026	0.091831	0.113216	0.363699	1.575403	0.706004	0.834830	...	-0.030137	-0.038739	-0.056497	-0.037710	-0.026549	-0.021879	4.825476	NaN	481.009629	NaN
4	NaN	NaN	NaN	0.176448	0.094282	0.117099	0.378197	1.839764	0.738640	1.071950	...	-0.028306	-0.038210	-0.040180	-0.027345	-0.026138	-0.021149	5.218871	NaN	482.819916	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
59	NaN	NaN	NaN	1.394205	0.839935	0.784691	1.821009	9.271523	4.754839	5.377768	...	0.025207	0.037807	0.028143	0.016645	0.015248	0.020823	12.862700	NaN	2157.871393	NaN
60	NaN	NaN	NaN	1.529994	0.894926	0.809959	1.889785	9.686563	5.295879	5.687977	...	0.028016	0.041946	0.040231	0.022928	0.019443	0.022756	12.874560	NaN	2210.936432	NaN
61	NaN	NaN	NaN	1.608454	0.989100	0.894706	1.951256	11.224542	5.707370	6.994751	...	0.036827	0.042347	0.048771	0.033156	0.044552	0.034289	12.892692	NaN	2226.127951	NaN
62	NaN	NaN	NaN	2.061820	1.219720	1.280772	1.965493	15.095252	7.876805	9.839396	...	0.056134	0.049357	0.051874	0.035976	0.055993	0.075071	14.651111	NaN	2284.051658	NaN
63	NaN	NaN	NaN	5.391649	3.217293	3.321567	5.991336	29.441589	16.791944	18.368778	...	0.220533	0.089766	0.080337	0.057303	0.061026	0.077897	15.420777	NaN	2441.219054	NaN

64 rows × 135 columns

columns=r.columns

len(r.columns)

135

135/5

27.0

for column in r:
    plt.figure(figsize=(10,4))
    plt.subplot(1,2,1)
    sns.histplot(r[column],bins=8,color="red",kde=True)
    plt.title(f"Histogram of "+column)
    plt.show()

for col in columns:
    plt.figure(figsize=(10,4))
    plt.subplot(1,2,1)
    sns.boxplot(x=r[col])
    plt.title("boxplot of" +col)
    plt.xlabel(col)
    plt.ylabel("Frequency")
    plt.show()

corr_matrix=r.corr()

correlation_matrix=r.corr()

plt.figure(figsize=(200,200))
sns.heatmap(data=correlation_matrix,vmax=None,annot=True,fmt=".2g")
plt.title("correlation Heatmap")
plt.show()
plt.tight_layout()

<Figure size 640x480 with 0 Axes>

pd.crosstab(r.Sex,r['Diagnosis(ALS)'])

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
File ~\anaconda3\Lib\site-packages\pandas\core\indexes\base.py:3791, in Index.get_loc(self, key)
   3790 try:
-> 3791     return self._engine.get_loc(casted_key)
   3792 except KeyError as err:

File index.pyx:152, in pandas._libs.index.IndexEngine.get_loc()

File index.pyx:181, in pandas._libs.index.IndexEngine.get_loc()

File pandas\_libs\hashtable_class_helper.pxi:7080, in pandas._libs.hashtable.PyObjectHashTable.get_item()

File pandas\_libs\hashtable_class_helper.pxi:7088, in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'Diagnosis(ALS)'

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)
Cell In[52], line 1
----> 1 pd.crosstab(r.Sex,r['Diagnosis(ALS)'])

File ~\anaconda3\Lib\site-packages\pandas\core\frame.py:3893, in DataFrame.__getitem__(self, key)
   3891 if self.columns.nlevels > 1:
   3892     return self._getitem_multilevel(key)
-> 3893 indexer = self.columns.get_loc(key)
   3894 if is_integer(indexer):
   3895     indexer = [indexer]

File ~\anaconda3\Lib\site-packages\pandas\core\indexes\base.py:3798, in Index.get_loc(self, key)
   3793     if isinstance(casted_key, slice) or (
   3794         isinstance(casted_key, abc.Iterable)
   3795         and any(isinstance(x, slice) for x in casted_key)
   3796     ):
   3797         raise InvalidIndexError(key)
-> 3798     raise KeyError(key) from err
   3799 except TypeError:
   3800     # If we have a listlike key, _check_indexing_error will raise
   3801     #  InvalidIndexError. Otherwise we fall through and re-raise
   3802     #  the TypeError.
   3803     self._check_indexing_error(key)

KeyError: 'Diagnosis(ALS)'

pd.crosstab(r.Age,r.Sex)

Sex	F	M
Age
34	0	1
35	0	1
37	1	0
38	0	2
39	2	0
40	1	1
41	0	1
43	0	1
45	1	0
49	0	1
50	3	0
51	0	1
52	1	1
53	2	0
55	3	0
57	2	3
58	1	3
59	1	0
60	3	3
61	0	2
62	2	0
63	3	1
64	3	0
65	1	0
66	0	1
67	2	3
68	1	2
69	0	1
70	1	0
80	0	1

sns.pairplot(data=r.iloc[:,2:15],palette=dict)

<seaborn.axisgrid.PairGrid at 0x24b1b7e2310>

from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier,BaggingClassifier,GradientBoostingClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold,StratifiedKFold,LeaveOneOut,ShuffleSplit
from sklearn.metrics import accuracy_score,classification_report
from sklearn.model_selection import cross_val_score
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report

x=r.iloc[:,:-1]
y=r.iloc[:,-1]

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=18)

x_train

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(6)	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}
30	102	F	53	0.561542	0.331788	0.345130	1.020709	6.074875	2.798090	3.526055	...	0.022664	0.008537	-0.000306	-0.012570	-0.048113	0.009073	-0.005201	12.036001	2526.285657	1200.269866
39	49	M	38	0.176448	0.103346	0.123381	0.649644	2.649815	1.410593	1.504265	...	0.016461	0.014798	-0.011568	-0.009276	-0.003996	-0.003248	-0.005049	10.074644	2119.782609	580.338238
54	113	F	62	0.823780	0.503064	0.497916	0.704065	6.861939	3.993216	4.174705	...	0.014494	0.003410	0.000716	-0.010791	0.004878	-0.005527	-0.001659	7.388631	2096.808356	737.085571
52	109	F	59	0.326851	0.215126	0.182667	0.304952	2.801295	1.669496	1.509331	...	-0.000688	-0.018500	0.030142	0.002111	0.006603	-0.013728	-0.021879	8.064921	2700.419449	1228.586973
45	81	F	60	0.286517	0.176603	0.195712	0.692300	1.847736	0.869278	1.099434	...	0.023767	-0.020693	0.019078	-0.034556	-0.006731	-0.025442	-0.005668	12.874560	2670.464441	1309.871125
61	127	F	67	0.383901	0.245923	0.251359	0.415136	4.148414	2.069757	2.527213	...	-0.005008	0.011685	0.007883	-0.014839	0.013859	0.011145	0.001418	12.564742	2526.285657	934.343638
28	98	M	68	1.076446	0.624824	0.561100	1.965493	7.001105	3.785627	4.033533	...	-0.011602	0.018274	0.004485	0.005101	-0.007367	0.007041	-0.001560	11.097431	3515.050257	2157.871393
58	121	F	67	0.237654	0.154117	0.154312	0.544602	3.583597	1.690501	1.840416	...	-0.027062	-0.002917	0.020006	-0.064556	0.014446	0.015248	-0.013882	9.311776	2670.464441	1087.940178
23	80	F	63	0.504802	0.253832	0.313823	1.229761	6.571067	2.833840	4.277576	...	0.013513	-0.003382	0.027770	-0.005112	-0.027102	0.012612	-0.010165	7.339732	3556.978755	2129.076098
33	6	M	41	1.063272	0.683918	0.504427	0.613402	3.176717	1.870164	1.590798	...	0.017293	-0.008880	-0.001511	0.003965	0.015240	-0.006500	-0.008723	10.482453	2263.284796	801.333727
41	61	F	37	0.818954	0.484998	0.511515	0.721296	4.942091	2.724820	3.320166	...	0.005945	0.021267	-0.008438	0.007339	-0.004838	-0.004133	0.000937	10.151495	2444.009071	1157.993834
15	55	M	61	1.177795	0.730069	0.569287	1.542224	5.883227	3.384535	2.875918	...	0.028733	-0.004708	-0.004383	0.006398	-0.014412	-0.005085	0.005530	7.148809	2051.627447	784.563460
31	2	F	64	0.219429	0.144385	0.171661	0.555528	2.054277	1.108746	1.260472	...	-0.011558	-0.004168	0.018603	0.019350	0.016342	0.014127	0.022756	10.121803	2988.533127	1332.559788
27	96	F	52	0.475047	0.308491	0.266091	0.396462	3.686641	1.999494	2.083195	...	0.009989	0.000009	0.042347	-0.003170	0.002103	0.011023	-0.031324	11.597077	2792.655884	1457.933269
26	94	F	55	0.764443	0.423008	0.472764	1.699466	8.254286	3.966819	5.010081	...	0.018794	0.036827	0.029426	-0.024056	-0.065735	0.012986	0.012941	9.482607	2471.097222	1019.521207
59	123	M	43	0.255799	0.123679	0.182658	0.505591	6.222031	2.876602	3.894294	...	-0.060395	0.220533	0.089766	-0.120838	-0.004221	-0.013165	0.004642	9.855665	3128.341308	1990.937097
35	24	M	60	0.391222	0.200687	0.232286	0.638498	2.324343	1.181015	1.475889	...	-0.005405	-0.006063	0.028443	-0.006618	0.003011	-0.005547	-0.002806	10.525555	2700.419449	1393.549002
40	53	M	60	0.487857	0.208116	0.282759	1.183502	4.734293	2.542676	3.053723	...	-0.003976	0.001242	0.005562	-0.000695	0.003333	0.004020	-0.005159	9.943562	2471.097222	1212.922300
29	100	M	69	0.511742	0.313666	0.320677	0.431433	7.417198	4.258109	4.961685	...	-0.013859	0.000308	-0.038984	0.048771	-0.014493	0.008647	-0.004524	2.512995	1233.583584	48.246203
0	8	M	58	0.321817	0.141230	0.199128	0.923634	6.044559	3.196477	3.770575	...	0.016809	-0.024467	-0.005300	0.051874	-0.037710	-0.026549	-0.021149	4.825476	2526.285657	833.498083
18	64	M	57	0.426554	0.202661	0.255198	0.885479	4.387137	1.892587	2.628737	...	0.003446	0.010420	0.005288	-0.006713	0.013147	-0.017816	0.017087	11.136041	2238.670803	930.223353
55	115	F	50	0.462076	0.269359	0.296952	0.909990	5.020638	2.305690	2.837745	...	0.001699	-0.001674	0.012043	-0.003015	0.022928	-0.005444	-0.006394	14.651111	3515.050257	2210.936432
13	48	F	63	0.805433	0.335434	0.487871	1.813700	4.485662	2.192828	2.864096	...	0.005770	-0.028306	-0.035823	-0.004287	-0.014985	-0.004156	-0.005061	7.029500	2730.764545	1288.920905
57	119	F	65	0.356684	0.233194	0.242305	0.410246	3.251335	1.867689	1.908461	...	0.005494	-0.003761	0.006982	0.012774	0.008384	0.002823	-0.014323	10.889792	2471.097222	1549.074209
6	27	M	57	0.691093	0.406901	0.406287	0.765986	6.168256	3.702088	3.286232	...	0.002661	-0.012605	0.013385	0.004513	0.001568	-0.008244	0.005801	5.945219	2313.388825	1219.744513
14	52	F	62	1.394205	0.839935	0.703224	1.362995	4.661601	2.402909	2.826132	...	-0.000823	0.025207	-0.002524	-0.006103	-0.012850	-0.015023	0.019711	12.862700	3092.653846	1552.852150
51	107	M	80	0.532330	0.296012	0.322217	0.650045	8.042171	4.754839	5.060159	...	-0.014078	0.010696	-0.003448	-0.015049	0.010195	-0.002152	0.001881	9.472404	2238.670803	1241.852695
9	32	M	61	0.387730	0.213745	0.249993	0.591160	3.351240	1.874979	2.075762	...	0.004241	0.006956	-0.002013	-0.000082	0.008275	-0.013829	-0.006955	7.572111	1780.825796	838.978523
3	22	F	70	0.455793	0.174870	0.243660	0.962641	2.883768	1.284926	1.915058	...	0.013213	-0.019285	-0.021768	0.020495	0.035976	-0.034648	0.008021	5.447137	1860.172768	359.409974
1	20	F	57	0.344026	0.177032	0.206458	0.827714	1.967728	0.856639	1.179851	...	0.019235	0.002485	-0.004535	-0.000225	-0.006977	-0.012510	0.014773	5.729322	1985.712014	561.802625
43	65	M	52	1.529994	0.894926	0.809959	1.715071	7.627483	4.321696	4.415383	...	0.015596	-0.012218	0.015828	-0.014697	0.010636	0.004654	-0.003235	7.758796	2761.507400	1641.852909
4	24	M	66	0.269335	0.143961	0.167465	0.547745	2.327924	1.164109	1.420891	...	0.002948	-0.005743	0.004726	-0.015247	0.003900	-0.007686	-0.003784	8.562517	2051.627447	817.111847
36	26	M	34	0.163026	0.094282	0.112654	0.378197	2.617874	1.361172	1.550565	...	-0.010711	0.006573	0.003950	-0.003954	0.001273	0.005890	0.000385	8.471564	2700.419449	1293.468915
11	42	M	67	1.608454	0.989100	0.894706	1.304613	6.031953	3.279233	3.729620	...	0.019701	0.004293	0.026891	0.080337	-0.007352	0.055993	0.075071	10.674106	2007.441819	481.009629
10	39	M	67	1.232990	0.561293	0.784691	1.889785	4.139457	1.915796	2.692091	...	0.031624	-0.018089	0.018493	0.006547	-0.004817	-0.003710	-0.000692	2.276702	1686.160000	669.461749
63	131	F	60	0.916706	0.566121	0.512857	1.467165	6.372832	3.251168	3.539229	...	-0.072828	-0.046235	0.041946	-0.065313	-0.016682	0.061026	-0.005883	6.972152	2792.655884	1518.529172
47	86	F	63	0.753234	0.467912	0.442792	0.540327	4.801768	2.677700	3.241265	...	-0.018937	0.011239	0.011488	0.015334	0.008337	0.005474	0.011687	10.515820	3057.463491	1494.054076
21	76	M	68	0.379367	0.223560	0.308426	1.821009	5.539475	2.551095	3.000675	...	0.008846	-0.006281	-0.004169	-0.008164	0.012667	-0.015442	0.001157	5.218871	1649.621788	177.843734
60	125	M	63	0.513175	0.296489	0.334845	0.729804	9.686563	4.327943	5.687977	...	-0.046223	0.028016	-0.038739	0.011588	-0.011281	-0.004294	0.011239	11.094558	1964.218942	601.076046
17	62	M	57	0.351191	0.165077	0.227554	0.849025	3.695872	1.776465	2.379529	...	0.024865	-0.008019	0.005046	0.023446	-0.000726	-0.016418	0.010174	6.031056	2074.091402	927.063276
34	16	M	38	0.415366	0.254119	0.243906	0.449362	2.394697	1.292778	1.468358	...	0.000016	0.008047	-0.005823	-0.006588	-0.000030	0.003137	-0.002440	8.531677	3515.050257	2441.219054
24	84	F	55	0.419330	0.255329	0.338319	0.486463	4.366452	1.932596	2.855240	...	-0.005714	0.012337	-0.005475	-0.001179	-0.002687	0.005369	0.034289	11.766102	2888.617021	1839.961952
8	31	M	67	0.537010	0.243234	0.318075	1.951256	6.568645	2.891654	4.620345	...	0.014234	0.013594	-0.003722	-0.003859	-0.011985	-0.027240	0.002325	8.760510	1840.022120	669.022078
2	21	F	58	0.264740	0.148228	0.177078	0.532566	1.850893	0.942743	1.071950	...	0.007199	-0.013927	0.007908	0.007960	-0.009022	-0.012488	-0.015588	8.258488	2364.695972	796.723440
50	99	F	57	0.098881	0.065791	0.092655	0.363699	0.883453	0.449099	0.497111	...	0.015152	-0.027019	0.037807	-0.019812	0.000436	-0.002840	-0.013161	10.108459	2143.018556	805.694015
46	85	F	55	0.454844	0.289458	0.293609	0.582757	2.124786	1.170689	1.182154	...	0.006111	0.003214	0.007520	-0.024862	0.016600	-0.015827	0.002088	12.189059	3092.653846	1551.286187
49	97	F	39	0.463874	0.290374	0.278926	0.550290	2.449028	1.372602	1.412486	...	-0.000234	0.011520	0.009453	0.002072	-0.002811	0.004577	-0.009058	10.616077	3164.536485	2037.766311
5	25	M	51	0.339593	0.182070	0.204186	0.505987	1.969217	0.834783	1.208688	...	0.009548	-0.005489	0.010164	-0.008341	-0.006132	0.005441	0.003568	9.810520	2143.018556	1004.727725
56	117	M	49	0.319535	0.143602	0.193376	0.846877	4.171980	1.868911	2.581316	...	-0.033465	0.019372	-0.041478	0.004583	-0.013913	-0.007205	0.013409	10.286022	1985.712014	804.666593
19	68	M	40	0.496922	0.213975	0.293201	0.957065	3.293700	1.672811	1.894214	...	0.023989	-0.030137	0.024769	0.000567	0.005071	-0.023693	0.009770	7.872279	2143.018556	985.160918
42	63	F	50	0.323175	0.126138	0.176197	0.907850	3.069980	1.372204	1.869070	...	0.004152	-0.001733	0.030566	-0.037259	-0.020167	-0.042955	-0.083977	9.167460	444.730268	1169.075556

51 rows × 134 columns

x_test

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(6)	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}
48	89	F	45	0.155762	0.091831	0.117099	0.575170	1.575403	0.738640	0.834830	...	0.002348	-0.002313	0.008766	0.006330	0.016645	-0.003417	0.002115	10.713432	3599.554394	2226.127951
38	42	M	60	0.182721	0.089174	0.113216	0.651748	1.839764	0.673977	1.084464	...	0.021454	0.007635	0.019134	0.013320	0.002002	-0.022146	0.005825	15.420777	2313.388825	1381.628235
53	111	F	60	0.121065	0.079473	0.101627	0.285497	1.117740	0.558948	0.615284	...	-0.005255	0.017626	-0.007311	-0.006541	-0.012625	0.013987	0.014222	11.261019	3201.250289	1960.299963
7	28	M	58	1.210548	0.726523	0.661670	1.205596	8.492104	4.109625	5.377768	...	0.007534	0.017088	0.015907	-0.006379	0.057303	-0.001919	-0.008007	8.422353	1964.218942	759.068477
22	78	F	64	0.437128	0.265519	0.349086	0.493971	3.205305	1.515726	2.119909	...	-0.060397	0.056134	-0.069202	-0.040180	-0.058987	0.044552	0.077897	2.986929	1800.351911	784.205580
12	46	F	50	0.199868	0.132266	0.157546	0.454599	1.467287	0.706004	0.819799	...	0.001819	0.011291	-0.001916	0.001513	-0.002502	0.002014	0.010446	10.950821	3164.536485	1553.425003
25	92	F	39	2.061820	1.219720	1.280772	1.306779	15.095252	7.876805	9.839396	...	0.009492	-0.033642	-0.032431	-0.056497	-0.003210	0.019443	0.004703	7.986808	3164.536485	1734.620853
44	77	F	40	0.349185	0.213207	0.227957	0.347673	3.395795	1.826527	2.123809	...	-0.042489	-0.021018	0.049357	0.005870	-0.027345	-0.026138	0.009430	10.594026	3515.050257	1925.062482
32	4	F	53	0.598550	0.350577	0.378646	0.654399	4.224992	2.312947	2.678596	...	0.001768	-0.003924	0.001995	0.004019	-0.007207	0.004614	0.003154	7.615608	2921.471038	1230.982918
20	72	F	64	0.797801	0.470116	0.522910	1.663179	7.778152	3.640445	4.355894	...	0.028207	-0.052002	-0.038210	0.028143	0.033156	0.010924	0.020823	5.924309	1880.538263	482.819916
37	28	M	35	0.758571	0.464961	0.413086	0.605323	9.271523	5.707370	5.150374	...	-0.003686	0.018992	0.034957	0.016890	-0.009376	-0.008998	-0.007465	12.892692	2888.617021	1653.804580
16	58	M	58	5.391649	3.217293	3.321567	5.991336	29.441589	16.791944	18.368778	...	-0.002691	0.008994	0.025390	0.040231	0.003503	-0.006546	-0.024835	8.008742	1921.927690	583.380671
62	129	F	68	1.336216	0.815757	0.733197	0.981928	11.224542	5.295879	6.994751	...	0.025679	0.015712	0.013437	0.025113	0.008852	-0.010132	-0.008458	10.670669	3201.250289	2284.051658

13 rows × 134 columns

y_train

30    1
39    0
54    0
52    0
45    0
61    0
28    1
58    0
23    1
33    0
41    0
15    1
31    0
27    1
26    1
59    0
35    0
40    0
29    1
0     1
18    1
55    0
13    1
57    0
6     1
14    1
51    0
9     1
3     1
1     1
43    0
4     1
36    0
11    1
10    1
63    0
47    0
21    1
60    0
17    1
34    0
24    1
8     1
2     1
50    0
46    0
49    0
5     1
56    0
19    1
42    0
Name: Diagnosis (ALS), dtype: int64

y_test

48    0
38    0
53    0
7     1
22    1
12    1
25    1
44    0
32    0
20    1
37    0
16    1
62    0
Name: Diagnosis (ALS), dtype: int64

y_test.shape

(13,)

ONE HOT ENCODER

from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline

categorical_cols=x_train.select_dtypes(include=["object"]).columns
print("CATEGORICAL COLUMNS :",categorical_cols)
numeric_cols=x_train.select_dtypes(include=["number"]).columns
numeric_cols=r[["Diagnosis (ALS)",'Age']]
print("NUMERIC COLUMNS:",numeric_cols)

CATEGORICAL COLUMNS : Index(['Sex'], dtype='object')
NUMERIC COLUMNS:     Diagnosis (ALS)  Age
0                 1   58
1                 1   57
2                 1   58
3                 1   70
4                 1   66
..              ...  ...
59                0   43
60                0   63
61                0   67
62                0   68
63                0   60

[64 rows x 2 columns]

 r.describe()

	ID	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	S11_a	...	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Diagnosis (ALS)
count	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	...	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000	64.000000
mean	67.875000	56.390625	0.658951	0.379242	0.395886	0.945496	5.072071	2.617924	3.078959	4.393513	...	0.003393	0.006224	-0.002889	-0.002152	-0.001969	0.001269	9.164473	2495.116475	1209.976405	0.484375
std	37.358198	10.203668	0.724002	0.435636	0.431926	0.791558	4.087221	2.289347	2.568471	3.327968	...	0.033268	0.024670	0.028315	0.019542	0.018012	0.020800	2.681449	617.755856	553.694046	0.503706
min	2.000000	34.000000	0.098881	0.065791	0.092655	0.285497	0.883453	0.449099	0.497111	0.804179	...	-0.052002	-0.069202	-0.120838	-0.065735	-0.042955	-0.083977	2.276702	444.730268	48.246203	0.000000
25%	31.750000	50.750000	0.325932	0.172422	0.198274	0.538387	2.641830	1.369446	1.508064	2.123761	...	-0.008234	-0.004222	-0.009654	-0.009853	-0.012674	-0.006534	7.604734	2051.627447	800.181156	0.000000
50%	66.500000	58.000000	0.458935	0.253976	0.293405	0.698183	4.198486	1.966045	2.653666	3.634994	...	0.000775	0.006272	-0.000937	-0.001614	-0.003921	0.000661	9.646564	2471.097222	1206.596083	0.000000
75%	98.250000	63.250000	0.772783	0.465699	0.476541	1.189025	6.259731	3.258184	3.801504	5.644808	...	0.011561	0.019092	0.006745	0.008349	0.005578	0.009515	10.757522	2938.236560	1551.677678	1.000000
max	131.000000	80.000000	5.391649	3.217293	3.321567	5.991336	29.441589	16.791944	18.368778	20.750202	...	0.220533	0.089766	0.080337	0.057303	0.061026	0.077897	15.420777	3599.554394	2441.219054	1.000000

8 rows × 134 columns

r.mode()

	ID	Sex	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	...	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Diagnosis (ALS)
0	24.0	F	60.0	0.098881	0.065791	0.092655	0.285497	0.883453	0.449099	0.497111	...	-0.052002	-0.069202	-0.120838	-0.065735	-0.042955	-0.083977	2.276702	3515.050257	48.246203	0.0
1	28.0	NaN	NaN	0.121065	0.079473	0.101627	0.304952	1.117740	0.558948	0.615284	...	-0.046235	-0.041478	-0.065313	-0.058987	-0.034648	-0.031324	2.512995	NaN	177.843734	NaN
2	42.0	NaN	NaN	0.155762	0.089174	0.112654	0.347673	1.467287	0.673977	0.819799	...	-0.033642	-0.038984	-0.064556	-0.048113	-0.027240	-0.024835	2.986929	NaN	359.409974	NaN
3	NaN	NaN	NaN	0.163026	0.091831	0.113216	0.363699	1.575403	0.706004	0.834830	...	-0.030137	-0.038739	-0.056497	-0.037710	-0.026549	-0.021879	4.825476	NaN	481.009629	NaN
4	NaN	NaN	NaN	0.176448	0.094282	0.117099	0.378197	1.839764	0.738640	1.071950	...	-0.028306	-0.038210	-0.040180	-0.027345	-0.026138	-0.021149	5.218871	NaN	482.819916	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
59	NaN	NaN	NaN	1.394205	0.839935	0.784691	1.821009	9.271523	4.754839	5.377768	...	0.025207	0.037807	0.028143	0.016645	0.015248	0.020823	12.862700	NaN	2157.871393	NaN
60	NaN	NaN	NaN	1.529994	0.894926	0.809959	1.889785	9.686563	5.295879	5.687977	...	0.028016	0.041946	0.040231	0.022928	0.019443	0.022756	12.874560	NaN	2210.936432	NaN
61	NaN	NaN	NaN	1.608454	0.989100	0.894706	1.951256	11.224542	5.707370	6.994751	...	0.036827	0.042347	0.048771	0.033156	0.044552	0.034289	12.892692	NaN	2226.127951	NaN
62	NaN	NaN	NaN	2.061820	1.219720	1.280772	1.965493	15.095252	7.876805	9.839396	...	0.056134	0.049357	0.051874	0.035976	0.055993	0.075071	14.651111	NaN	2284.051658	NaN
63	NaN	NaN	NaN	5.391649	3.217293	3.321567	5.991336	29.441589	16.791944	18.368778	...	0.220533	0.089766	0.080337	0.057303	0.061026	0.077897	15.420777	NaN	2441.219054	NaN

64 rows × 135 columns

r.corr

<bound method DataFrame.corr of      ID Sex  Age      J1_a      J3_a      J5_a     J55_a       S1_a      S3_a  \
0     8   M   58  0.321817  0.141230  0.199128  0.923634   6.044559  3.196477   
1    20   F   57  0.344026  0.177032  0.206458  0.827714   1.967728  0.856639   
2    21   F   58  0.264740  0.148228  0.177078  0.532566   1.850893  0.942743   
3    22   F   70  0.455793  0.174870  0.243660  0.962641   2.883768  1.284926   
4    24   M   66  0.269335  0.143961  0.167465  0.547745   2.327924  1.164109   
..  ...  ..  ...       ...       ...       ...       ...        ...       ...   
59  123   M   43  0.255799  0.123679  0.182658  0.505591   6.222031  2.876602   
60  125   M   63  0.513175  0.296489  0.334845  0.729804   9.686563  4.327943   
61  127   F   67  0.383901  0.245923  0.251359  0.415136   4.148414  2.069757   
62  129   F   68  1.336216  0.815757  0.733197  0.981928  11.224542  5.295879   
63  131   F   60  0.916706  0.566121  0.512857  1.467165   6.372832  3.251168   

        S5_a  ...   dCCi(7)   dCCi(8)   dCCi(9)  dCCi(10)  dCCi(11)  dCCi(12)  \
0   3.770575  ... -0.024467 -0.005300  0.051874 -0.037710 -0.026549 -0.021149   
1   1.179851  ...  0.002485 -0.004535 -0.000225 -0.006977 -0.012510  0.014773   
2   1.071950  ... -0.013927  0.007908  0.007960 -0.009022 -0.012488 -0.015588   
3   1.915058  ... -0.019285 -0.021768  0.020495  0.035976 -0.034648  0.008021   
4   1.420891  ... -0.005743  0.004726 -0.015247  0.003900 -0.007686 -0.003784   
..       ...  ...       ...       ...       ...       ...       ...       ...   
59  3.894294  ...  0.220533  0.089766 -0.120838 -0.004221 -0.013165  0.004642   
60  5.687977  ...  0.028016 -0.038739  0.011588 -0.011281 -0.004294  0.011239   
61  2.527213  ...  0.011685  0.007883 -0.014839  0.013859  0.011145  0.001418   
62  6.994751  ...  0.015712  0.013437  0.025113  0.008852 -0.010132 -0.008458   
63  3.539229  ... -0.046235  0.041946 -0.065313 -0.016682  0.061026 -0.005883   

          d_1         F2_i    F2_{conv}  Diagnosis (ALS)  
0    4.825476  2526.285657   833.498083                1  
1    5.729322  1985.712014   561.802625                1  
2    8.258488  2364.695972   796.723440                1  
3    5.447137  1860.172768   359.409974                1  
4    8.562517  2051.627447   817.111847                1  
..        ...          ...          ...              ...  
59   9.855665  3128.341308  1990.937097                0  
60  11.094558  1964.218942   601.076046                0  
61  12.564742  2526.285657   934.343638                0  
62  10.670669  3201.250289  2284.051658                0  
63   6.972152  2792.655884  1518.529172                0  

[64 rows x 135 columns]>

preprocessor=ColumnTransformer(
    transformers=[
        ('dog',
         OneHotEncoder(handle_unknown="ignore"),
         categorical_cols)
        
    ],
    remainder="passthrough"
)

x_train_transformed=preprocessor.fit_transform(x_train)

x_train_transformed

array([[1.00000000e+00, 0.00000000e+00, 1.02000000e+02, ...,
        1.20360009e+01, 2.52628566e+03, 1.20026987e+03],
       [0.00000000e+00, 1.00000000e+00, 4.90000000e+01, ...,
        1.00746439e+01, 2.11978261e+03, 5.80338238e+02],
       [1.00000000e+00, 0.00000000e+00, 1.13000000e+02, ...,
        7.38863107e+00, 2.09680836e+03, 7.37085571e+02],
       ...,
       [0.00000000e+00, 1.00000000e+00, 1.17000000e+02, ...,
        1.02860219e+01, 1.98571201e+03, 8.04666593e+02],
       [0.00000000e+00, 1.00000000e+00, 6.80000000e+01, ...,
        7.87227878e+00, 2.14301856e+03, 9.85160918e+02],
       [1.00000000e+00, 0.00000000e+00, 6.30000000e+01, ...,
        9.16746005e+00, 4.44730268e+02, 1.16907556e+03]])

one_hot_encoded_columns=preprocessor.named_transformers_['dog'].get_feature_names_out(categorical_cols)

all_columns=list(one_hot_encoded_columns) + [col for col in x_train.columns if col not in categorical_cols]

x_train_transformed_df=pd.DataFrame(x_train_transformed, columns=all_columns)
one_hot_encoded_columns

array(['Sex_F', 'Sex_M'], dtype=object)

x_train_transformed_df

	Sex_F	Sex_M	ID	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	...	dCCi(6)	dCCi(7)	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}
0	1.0	0.0	102.0	53.0	0.561542	0.331788	0.345130	1.020709	6.074875	2.798090	...	0.022664	0.008537	-0.000306	-0.012570	-0.048113	0.009073	-0.005201	12.036001	2526.285657	1200.269866
1	0.0	1.0	49.0	38.0	0.176448	0.103346	0.123381	0.649644	2.649815	1.410593	...	0.016461	0.014798	-0.011568	-0.009276	-0.003996	-0.003248	-0.005049	10.074644	2119.782609	580.338238
2	1.0	0.0	113.0	62.0	0.823780	0.503064	0.497916	0.704065	6.861939	3.993216	...	0.014494	0.003410	0.000716	-0.010791	0.004878	-0.005527	-0.001659	7.388631	2096.808356	737.085571
3	1.0	0.0	109.0	59.0	0.326851	0.215126	0.182667	0.304952	2.801295	1.669496	...	-0.000688	-0.018500	0.030142	0.002111	0.006603	-0.013728	-0.021879	8.064921	2700.419449	1228.586973
4	1.0	0.0	81.0	60.0	0.286517	0.176603	0.195712	0.692300	1.847736	0.869278	...	0.023767	-0.020693	0.019078	-0.034556	-0.006731	-0.025442	-0.005668	12.874560	2670.464441	1309.871125
5	1.0	0.0	127.0	67.0	0.383901	0.245923	0.251359	0.415136	4.148414	2.069757	...	-0.005008	0.011685	0.007883	-0.014839	0.013859	0.011145	0.001418	12.564742	2526.285657	934.343638
6	0.0	1.0	98.0	68.0	1.076446	0.624824	0.561100	1.965493	7.001105	3.785627	...	-0.011602	0.018274	0.004485	0.005101	-0.007367	0.007041	-0.001560	11.097431	3515.050257	2157.871393
7	1.0	0.0	121.0	67.0	0.237654	0.154117	0.154312	0.544602	3.583597	1.690501	...	-0.027062	-0.002917	0.020006	-0.064556	0.014446	0.015248	-0.013882	9.311776	2670.464441	1087.940178
8	1.0	0.0	80.0	63.0	0.504802	0.253832	0.313823	1.229761	6.571067	2.833840	...	0.013513	-0.003382	0.027770	-0.005112	-0.027102	0.012612	-0.010165	7.339732	3556.978755	2129.076098
9	0.0	1.0	6.0	41.0	1.063272	0.683918	0.504427	0.613402	3.176717	1.870164	...	0.017293	-0.008880	-0.001511	0.003965	0.015240	-0.006500	-0.008723	10.482453	2263.284796	801.333727
10	1.0	0.0	61.0	37.0	0.818954	0.484998	0.511515	0.721296	4.942091	2.724820	...	0.005945	0.021267	-0.008438	0.007339	-0.004838	-0.004133	0.000937	10.151495	2444.009071	1157.993834
11	0.0	1.0	55.0	61.0	1.177795	0.730069	0.569287	1.542224	5.883227	3.384535	...	0.028733	-0.004708	-0.004383	0.006398	-0.014412	-0.005085	0.005530	7.148809	2051.627447	784.563460
12	1.0	0.0	2.0	64.0	0.219429	0.144385	0.171661	0.555528	2.054277	1.108746	...	-0.011558	-0.004168	0.018603	0.019350	0.016342	0.014127	0.022756	10.121803	2988.533127	1332.559788
13	1.0	0.0	96.0	52.0	0.475047	0.308491	0.266091	0.396462	3.686641	1.999494	...	0.009989	0.000009	0.042347	-0.003170	0.002103	0.011023	-0.031324	11.597077	2792.655884	1457.933269
14	1.0	0.0	94.0	55.0	0.764443	0.423008	0.472764	1.699466	8.254286	3.966819	...	0.018794	0.036827	0.029426	-0.024056	-0.065735	0.012986	0.012941	9.482607	2471.097222	1019.521207
15	0.0	1.0	123.0	43.0	0.255799	0.123679	0.182658	0.505591	6.222031	2.876602	...	-0.060395	0.220533	0.089766	-0.120838	-0.004221	-0.013165	0.004642	9.855665	3128.341308	1990.937097
16	0.0	1.0	24.0	60.0	0.391222	0.200687	0.232286	0.638498	2.324343	1.181015	...	-0.005405	-0.006063	0.028443	-0.006618	0.003011	-0.005547	-0.002806	10.525555	2700.419449	1393.549002
17	0.0	1.0	53.0	60.0	0.487857	0.208116	0.282759	1.183502	4.734293	2.542676	...	-0.003976	0.001242	0.005562	-0.000695	0.003333	0.004020	-0.005159	9.943562	2471.097222	1212.922300
18	0.0	1.0	100.0	69.0	0.511742	0.313666	0.320677	0.431433	7.417198	4.258109	...	-0.013859	0.000308	-0.038984	0.048771	-0.014493	0.008647	-0.004524	2.512995	1233.583584	48.246203
19	0.0	1.0	8.0	58.0	0.321817	0.141230	0.199128	0.923634	6.044559	3.196477	...	0.016809	-0.024467	-0.005300	0.051874	-0.037710	-0.026549	-0.021149	4.825476	2526.285657	833.498083
20	0.0	1.0	64.0	57.0	0.426554	0.202661	0.255198	0.885479	4.387137	1.892587	...	0.003446	0.010420	0.005288	-0.006713	0.013147	-0.017816	0.017087	11.136041	2238.670803	930.223353
21	1.0	0.0	115.0	50.0	0.462076	0.269359	0.296952	0.909990	5.020638	2.305690	...	0.001699	-0.001674	0.012043	-0.003015	0.022928	-0.005444	-0.006394	14.651111	3515.050257	2210.936432
22	1.0	0.0	48.0	63.0	0.805433	0.335434	0.487871	1.813700	4.485662	2.192828	...	0.005770	-0.028306	-0.035823	-0.004287	-0.014985	-0.004156	-0.005061	7.029500	2730.764545	1288.920905
23	1.0	0.0	119.0	65.0	0.356684	0.233194	0.242305	0.410246	3.251335	1.867689	...	0.005494	-0.003761	0.006982	0.012774	0.008384	0.002823	-0.014323	10.889792	2471.097222	1549.074209
24	0.0	1.0	27.0	57.0	0.691093	0.406901	0.406287	0.765986	6.168256	3.702088	...	0.002661	-0.012605	0.013385	0.004513	0.001568	-0.008244	0.005801	5.945219	2313.388825	1219.744513
25	1.0	0.0	52.0	62.0	1.394205	0.839935	0.703224	1.362995	4.661601	2.402909	...	-0.000823	0.025207	-0.002524	-0.006103	-0.012850	-0.015023	0.019711	12.862700	3092.653846	1552.852150
26	0.0	1.0	107.0	80.0	0.532330	0.296012	0.322217	0.650045	8.042171	4.754839	...	-0.014078	0.010696	-0.003448	-0.015049	0.010195	-0.002152	0.001881	9.472404	2238.670803	1241.852695
27	0.0	1.0	32.0	61.0	0.387730	0.213745	0.249993	0.591160	3.351240	1.874979	...	0.004241	0.006956	-0.002013	-0.000082	0.008275	-0.013829	-0.006955	7.572111	1780.825796	838.978523
28	1.0	0.0	22.0	70.0	0.455793	0.174870	0.243660	0.962641	2.883768	1.284926	...	0.013213	-0.019285	-0.021768	0.020495	0.035976	-0.034648	0.008021	5.447137	1860.172768	359.409974
29	1.0	0.0	20.0	57.0	0.344026	0.177032	0.206458	0.827714	1.967728	0.856639	...	0.019235	0.002485	-0.004535	-0.000225	-0.006977	-0.012510	0.014773	5.729322	1985.712014	561.802625
30	0.0	1.0	65.0	52.0	1.529994	0.894926	0.809959	1.715071	7.627483	4.321696	...	0.015596	-0.012218	0.015828	-0.014697	0.010636	0.004654	-0.003235	7.758796	2761.507400	1641.852909
31	0.0	1.0	24.0	66.0	0.269335	0.143961	0.167465	0.547745	2.327924	1.164109	...	0.002948	-0.005743	0.004726	-0.015247	0.003900	-0.007686	-0.003784	8.562517	2051.627447	817.111847
32	0.0	1.0	26.0	34.0	0.163026	0.094282	0.112654	0.378197	2.617874	1.361172	...	-0.010711	0.006573	0.003950	-0.003954	0.001273	0.005890	0.000385	8.471564	2700.419449	1293.468915
33	0.0	1.0	42.0	67.0	1.608454	0.989100	0.894706	1.304613	6.031953	3.279233	...	0.019701	0.004293	0.026891	0.080337	-0.007352	0.055993	0.075071	10.674106	2007.441819	481.009629
34	0.0	1.0	39.0	67.0	1.232990	0.561293	0.784691	1.889785	4.139457	1.915796	...	0.031624	-0.018089	0.018493	0.006547	-0.004817	-0.003710	-0.000692	2.276702	1686.160000	669.461749
35	1.0	0.0	131.0	60.0	0.916706	0.566121	0.512857	1.467165	6.372832	3.251168	...	-0.072828	-0.046235	0.041946	-0.065313	-0.016682	0.061026	-0.005883	6.972152	2792.655884	1518.529172
36	1.0	0.0	86.0	63.0	0.753234	0.467912	0.442792	0.540327	4.801768	2.677700	...	-0.018937	0.011239	0.011488	0.015334	0.008337	0.005474	0.011687	10.515820	3057.463491	1494.054076
37	0.0	1.0	76.0	68.0	0.379367	0.223560	0.308426	1.821009	5.539475	2.551095	...	0.008846	-0.006281	-0.004169	-0.008164	0.012667	-0.015442	0.001157	5.218871	1649.621788	177.843734
38	0.0	1.0	125.0	63.0	0.513175	0.296489	0.334845	0.729804	9.686563	4.327943	...	-0.046223	0.028016	-0.038739	0.011588	-0.011281	-0.004294	0.011239	11.094558	1964.218942	601.076046
39	0.0	1.0	62.0	57.0	0.351191	0.165077	0.227554	0.849025	3.695872	1.776465	...	0.024865	-0.008019	0.005046	0.023446	-0.000726	-0.016418	0.010174	6.031056	2074.091402	927.063276
40	0.0	1.0	16.0	38.0	0.415366	0.254119	0.243906	0.449362	2.394697	1.292778	...	0.000016	0.008047	-0.005823	-0.006588	-0.000030	0.003137	-0.002440	8.531677	3515.050257	2441.219054
41	1.0	0.0	84.0	55.0	0.419330	0.255329	0.338319	0.486463	4.366452	1.932596	...	-0.005714	0.012337	-0.005475	-0.001179	-0.002687	0.005369	0.034289	11.766102	2888.617021	1839.961952
42	0.0	1.0	31.0	67.0	0.537010	0.243234	0.318075	1.951256	6.568645	2.891654	...	0.014234	0.013594	-0.003722	-0.003859	-0.011985	-0.027240	0.002325	8.760510	1840.022120	669.022078
43	1.0	0.0	21.0	58.0	0.264740	0.148228	0.177078	0.532566	1.850893	0.942743	...	0.007199	-0.013927	0.007908	0.007960	-0.009022	-0.012488	-0.015588	8.258488	2364.695972	796.723440
44	1.0	0.0	99.0	57.0	0.098881	0.065791	0.092655	0.363699	0.883453	0.449099	...	0.015152	-0.027019	0.037807	-0.019812	0.000436	-0.002840	-0.013161	10.108459	2143.018556	805.694015
45	1.0	0.0	85.0	55.0	0.454844	0.289458	0.293609	0.582757	2.124786	1.170689	...	0.006111	0.003214	0.007520	-0.024862	0.016600	-0.015827	0.002088	12.189059	3092.653846	1551.286187
46	1.0	0.0	97.0	39.0	0.463874	0.290374	0.278926	0.550290	2.449028	1.372602	...	-0.000234	0.011520	0.009453	0.002072	-0.002811	0.004577	-0.009058	10.616077	3164.536485	2037.766311
47	0.0	1.0	25.0	51.0	0.339593	0.182070	0.204186	0.505987	1.969217	0.834783	...	0.009548	-0.005489	0.010164	-0.008341	-0.006132	0.005441	0.003568	9.810520	2143.018556	1004.727725
48	0.0	1.0	117.0	49.0	0.319535	0.143602	0.193376	0.846877	4.171980	1.868911	...	-0.033465	0.019372	-0.041478	0.004583	-0.013913	-0.007205	0.013409	10.286022	1985.712014	804.666593
49	0.0	1.0	68.0	40.0	0.496922	0.213975	0.293201	0.957065	3.293700	1.672811	...	0.023989	-0.030137	0.024769	0.000567	0.005071	-0.023693	0.009770	7.872279	2143.018556	985.160918
50	1.0	0.0	63.0	50.0	0.323175	0.126138	0.176197	0.907850	3.069980	1.372204	...	0.004152	-0.001733	0.030566	-0.037259	-0.020167	-0.042955	-0.083977	9.167460	444.730268	1169.075556

51 rows × 135 columns

DECISIONTREECLASSIFIER

models=DecisionTreeClassifier(criterion="entropy",max_depth=10,min_samples_split=3)

models.fit(x_train_transformed_df,y_train)

DecisionTreeClassifier(criterion='entropy', max_depth=10, min_samples_split=3)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

from sklearn.model_selection import GridSearchCV,RandomizedSearchCV

pred=models.predict(x_train_transformed_df)
pred

array([1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0,
       1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1,
       0, 0, 0, 1, 0, 1, 0], dtype=int64)

accuracy_score(y_train,pred)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[90], line 1
----> 1 accuracy_score(y_train,pred)

File ~\anaconda3\Lib\site-packages\sklearn\utils\_param_validation.py:192, in validate_params.<locals>.decorator.<locals>.wrapper(*args, **kwargs)
    187 validate_parameter_constraints(
    188     parameter_constraints, params, caller_name=func.__qualname__
    189 )
    191 try:
--> 192     return func(*args, **kwargs)
    193 except InvalidParameterError as e:
    194     # When the function is just a wrapper around an estimator, we allow
    195     # the function to delegate validation to the estimator, but we replace
    196     # the name of the estimator by the name of the function in the error
    197     # message to avoid confusion.
    198     msg = re.sub(
    199         r"parameter of \w+ must be",
    200         f"parameter of {func.__qualname__} must be",
    201         str(e),
    202     )

File ~\anaconda3\Lib\site-packages\sklearn\metrics\_classification.py:221, in accuracy_score(y_true, y_pred, normalize, sample_weight)
    155 """Accuracy classification score.
    156 
    157 In multilabel classification, this function computes subset accuracy:
   (...)
    217 0.5
    218 """
    220 # Compute accuracy for each possible representation
--> 221 y_type, y_true, y_pred = _check_targets(y_true, y_pred)
    222 check_consistent_length(y_true, y_pred, sample_weight)
    223 if y_type.startswith("multilabel"):

File ~\anaconda3\Lib\site-packages\sklearn\metrics\_classification.py:86, in _check_targets(y_true, y_pred)
     59 def _check_targets(y_true, y_pred):
     60     """Check that y_true and y_pred belong to the same classification task.
     61 
     62     This converts multiclass or binary types to a common shape, and raises a
   (...)
     84     y_pred : array or indicator matrix
     85     """
---> 86     check_consistent_length(y_true, y_pred)
     87     type_true = type_of_target(y_true, input_name="y_true")
     88     type_pred = type_of_target(y_pred, input_name="y_pred")

File ~\anaconda3\Lib\site-packages\sklearn\utils\validation.py:397, in check_consistent_length(*arrays)
    395 uniques = np.unique(lengths)
    396 if len(uniques) > 1:
--> 397     raise ValueError(
    398         "Found input variables with inconsistent numbers of samples: %r"
    399         % [int(l) for l in lengths]
    400     )

ValueError: Found input variables with inconsistent numbers of samples: [54, 51]

print(classification_report(y_train,pred))

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[91], line 1
----> 1 print(classification_report(y_train,pred))

File ~\anaconda3\Lib\site-packages\sklearn\metrics\_classification.py:2310, in classification_report(y_true, y_pred, labels, target_names, sample_weight, digits, output_dict, zero_division)
   2195 def classification_report(
   2196     y_true,
   2197     y_pred,
   (...)
   2204     zero_division="warn",
   2205 ):
   2206     """Build a text report showing the main classification metrics.
   2207 
   2208     Read more in the :ref:`User Guide <classification_report>`.
   (...)
   2307     <BLANKLINE>
   2308     """
-> 2310     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
   2312     if labels is None:
   2313         labels = unique_labels(y_true, y_pred)

File ~\anaconda3\Lib\site-packages\sklearn\metrics\_classification.py:86, in _check_targets(y_true, y_pred)
     59 def _check_targets(y_true, y_pred):
     60     """Check that y_true and y_pred belong to the same classification task.
     61 
     62     This converts multiclass or binary types to a common shape, and raises a
   (...)
     84     y_pred : array or indicator matrix
     85     """
---> 86     check_consistent_length(y_true, y_pred)
     87     type_true = type_of_target(y_true, input_name="y_true")
     88     type_pred = type_of_target(y_pred, input_name="y_pred")

File ~\anaconda3\Lib\site-packages\sklearn\utils\validation.py:397, in check_consistent_length(*arrays)
    395 uniques = np.unique(lengths)
    396 if len(uniques) > 1:
--> 397     raise ValueError(
    398         "Found input variables with inconsistent numbers of samples: %r"
    399         % [int(l) for l in lengths]
    400     )

ValueError: Found input variables with inconsistent numbers of samples: [54, 51]

LOGISTICREGRESSION

models=LogisticRegression()
models.fit(x_train_transformed_df,y_train)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[92], line 2
      1 models=LogisticRegression()
----> 2 models.fit(x_train_transformed_df,y_train)

File ~\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:1196, in LogisticRegression.fit(self, X, y, sample_weight)
   1193 else:
   1194     _dtype = [np.float64, np.float32]
-> 1196 X, y = self._validate_data(
   1197     X,
   1198     y,
   1199     accept_sparse="csr",
   1200     dtype=_dtype,
   1201     order="C",
   1202     accept_large_sparse=solver not in ["liblinear", "sag", "saga"],
   1203 )
   1204 check_classification_targets(y)
   1205 self.classes_ = np.unique(y)

File ~\anaconda3\Lib\site-packages\sklearn\base.py:584, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, **check_params)
    582         y = check_array(y, input_name="y", **check_y_params)
    583     else:
--> 584         X, y = check_X_y(X, y, **check_params)
    585     out = X, y
    587 if not no_val_X and check_params.get("ensure_2d", True):

File ~\anaconda3\Lib\site-packages\sklearn\utils\validation.py:1124, in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)
   1106 X = check_array(
   1107     X,
   1108     accept_sparse=accept_sparse,
   (...)
   1119     input_name="X",
   1120 )
   1122 y = _check_y(y, multi_output=multi_output, y_numeric=y_numeric, estimator=estimator)
-> 1124 check_consistent_length(X, y)
   1126 return X, y

File ~\anaconda3\Lib\site-packages\sklearn\utils\validation.py:397, in check_consistent_length(*arrays)
    395 uniques = np.unique(lengths)
    396 if len(uniques) > 1:
--> 397     raise ValueError(
    398         "Found input variables with inconsistent numbers of samples: %r"
    399         % [int(l) for l in lengths]
    400     )

ValueError: Found input variables with inconsistent numbers of samples: [51, 54]

GRIDSEARCH

x=pd.get_dummies(x)

x

	ID	Age	J1_a	J3_a	J5_a	J55_a	S1_a	S3_a	S5_a	S11_a	...	dCCi(8)	dCCi(9)	dCCi(10)	dCCi(11)	dCCi(12)	d_1	F2_i	F2_{conv}	Sex_F	Sex_M
0	8	58	0.321817	0.141230	0.199128	0.923634	6.044559	3.196477	3.770575	5.709480	...	-0.005300	0.051874	-0.037710	-0.026549	-0.021149	4.825476	2526.285657	833.498083	False	True
1	20	57	0.344026	0.177032	0.206458	0.827714	1.967728	0.856639	1.179851	2.050048	...	-0.004535	-0.000225	-0.006977	-0.012510	0.014773	5.729322	1985.712014	561.802625	True	False
2	21	58	0.264740	0.148228	0.177078	0.532566	1.850893	0.942743	1.071950	1.502212	...	0.007908	0.007960	-0.009022	-0.012488	-0.015588	8.258488	2364.695972	796.723440	True	False
3	22	70	0.455793	0.174870	0.243660	0.962641	2.883768	1.284926	1.915058	2.929953	...	-0.021768	0.020495	0.035976	-0.034648	0.008021	5.447137	1860.172768	359.409974	True	False
4	24	66	0.269335	0.143961	0.167465	0.547745	2.327924	1.164109	1.420891	2.141512	...	0.004726	-0.015247	0.003900	-0.007686	-0.003784	8.562517	2051.627447	817.111847	False	True
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
59	123	43	0.255799	0.123679	0.182658	0.505591	6.222031	2.876602	3.894294	5.697601	...	0.089766	-0.120838	-0.004221	-0.013165	0.004642	9.855665	3128.341308	1990.937097	False	True
60	125	63	0.513175	0.296489	0.334845	0.729804	9.686563	4.327943	5.687977	9.912757	...	-0.038739	0.011588	-0.011281	-0.004294	0.011239	11.094558	1964.218942	601.076046	False	True
61	127	67	0.383901	0.245923	0.251359	0.415136	4.148414	2.069757	2.527213	3.362755	...	0.007883	-0.014839	0.013859	0.011145	0.001418	12.564742	2526.285657	934.343638	True	False
62	129	68	1.336216	0.815757	0.733197	0.981928	11.224542	5.295879	6.994751	11.706090	...	0.013437	0.025113	0.008852	-0.010132	-0.008458	10.670669	3201.250289	2284.051658	True	False
63	131	60	0.916706	0.566121	0.512857	1.467165	6.372832	3.251168	3.539229	5.627211	...	0.041946	-0.065313	-0.016682	0.061026	-0.005883	6.972152	2792.655884	1518.529172	True	False

64 rows × 135 columns

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.15,random_state=42)

model=DecisionTreeClassifier()

grid={
    'criterion':["gini"],
    'min_samples_split':[2,4,6,8],
    'max_depth':[10,6,8]
}

gscv=GridSearchCV(estimator=model,param_grid=grid,cv=5,n_jobs-1)

  Cell In[98], line 1
    gscv=GridSearchCV(estimator=model,param_grid=grid,cv=5,n_jobs-1)
                                                                   ^
SyntaxError: positional argument follows keyword argument

gscv.fit(x_train,y_train)